Jove
Visualize
Contact Us

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Skinned Tetrahedral Mesh for Hair Animation and Hair-Water Interaction.

IEEE transactions on visualization and computer graphics·2018
Same author

Real-Time Interactive Tree Animation.

IEEE transactions on visualization and computer graphics·2017
Same author

Energy Conservation for the Simulation of Deformable Bodies.

IEEE transactions on visualization and computer graphics·2012
Same author

Robust high-resolution cloth using parallelism, history-based collisions, and accurate friction.

IEEE transactions on visualization and computer graphics·2009
Same author

Two-way coupled SPH and particle level set fluid simulation.

IEEE transactions on visualization and computer graphics·2008
Same author

Impulse-based control of joints and muscles.

IEEE transactions on visualization and computer graphics·2007
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 25, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

2.8K

Local Geometric Indexing of High Resolution Data for Facial Reconstruction From Sparse Markers.

Matthew Cong, Lana Lan, Ronald Fedkiw

    IEEE Transactions on Visualization and Computer Graphics
    |June 26, 2023
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel method for sparse motion capture data by finding matching geometry in high-resolution datasets, avoiding traditional blendshape overfitting and smoothness underfitting. This approach leverages extensive data, including simulated datasets, for more accurate motion capture reconstruction.

    More Related Videos

    Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain
    06:52

    Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

    Published on: January 26, 2024

    2.1K
    Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
    05:49

    Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

    Published on: February 23, 2024

    896

    Related Experiment Videos

    Last Updated: Jul 25, 2025

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
    10:23

    Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

    Published on: September 8, 2023

    2.8K
    Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain
    06:52

    Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

    Published on: January 26, 2024

    2.1K
    Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
    05:49

    Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

    Published on: February 23, 2024

    896

    Area of Science:

    • Computer Graphics
    • Machine Learning
    • Motion Capture

    Background:

    • Sparse motion capture marker data presents challenges in balancing model complexity and data fidelity.
    • Traditional methods like blendshape models risk overfitting, while smoothness constraints can lead to underfitting.
    • The increasing availability of high-resolution datasets offers new opportunities for motion capture.

    Purpose of the Study:

    • To develop a new approach for sparse motion capture data that avoids overfitting and underfitting issues.
    • To utilize high-resolution datasets to find local geometry that accurately fits individual motion capture markers.
    • To augment datasets with physically simulated data that conforms to the same manifold as real-world data.

    Main Methods:

    • Instead of fitting parameterized models or interpolating surfaces, the method searches for matching instances within a high-resolution dataset.
    • The approach leverages the abundance of data, a key principle in machine learning.
    • Dataset augmentation is performed using targeted physical simulations designed to generate data on the same manifold as the original high-resolution dataset.

    Main Results:

    • The proposed method effectively addresses the overfitting/underfitting dilemma in sparse motion capture.
    • By matching markers to local geometry in high-resolution data, more accurate reconstructions are achieved.
    • Simulated data generation enhances the dataset, improving the robustness of the fitting process.

    Conclusions:

    • This data-driven approach offers a promising alternative to traditional methods for sparse motion capture.
    • Leveraging large datasets and targeted simulations leads to improved accuracy and detail in motion capture.
    • The method's success highlights the potential of manifold-aligned data augmentation in computer graphics and animation.